INDEX

Explanations

negative connotations associated with various situations or themes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.97

rungsseite

-0.83

AndEndTag

-0.81

 nonUne

-0.79

PreInfinity

-0.76

verwijspagina

-0.73

帖最后由

-0.68

السكان

-0.67

ContentAsync

-0.66

FunctionFlags

-0.65

POSITIVE LOGITS

 auber

0.53

 Bunt

0.51

hartt

0.51

.[/

0.50

 Bater

0.48

 almend

0.48

 Chees

0.48

 ListTile

0.47

Ips

0.47

 Audiodateien

0.47

Activations Density 0.323%

negative connotations associated with various situations or themes

No Comments

No Known Activations